71,235 visible repositories in the index
1–15 of 15 · Most stars
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
An app that brings language models directly to your phone.
Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
演示站可以免费使用deepseek-r1满血模型进行AI对话，并支持使用stablediffusion模型画图。本项目是PHP版调用DeepSeek第三方接口进行问答和画图，采用Stream流模式通信，一边生成一边输出。前端采用EventSource，支持Markdown格式解析，支持公式显示，代码有着色处理，支持画图。页面UI简洁，支持上下文连续会话。源码只有几个文件，没用任何框架，支持所有PHP版本，全部开源，极易二开，适合PHP初学者。保姆级教程，账号等周边资源，欢迎进群交流，一切全免费。
Reference implementation for DPO (Direct Preference Optimization)
Concatenate a directory full of files into a single prompt for use with LLMs
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption
Laravel’s #1 real-time chat package. Direct messages, groups, voice notes, and much more, with a full messenger UI — plus a headless API. Install in one command.
Native iOS and Android client for Open WebUI, direct OpenAI-compatible, Ollama, and Hermes agents.
Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
Agentic Chat Interface directly in Neovim with ACP providers from Claude-Code, Gemini, Codex, OpenCode, and Cursor-agent
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.
Run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.